FLUX.1-Krea-dev-SDNQ-uint4-svd-r32

Name: FLUX.1-Krea-dev-SDNQ-uint4-svd-r32
Author: Disty0

—

Disty0

Image Model

OTHER

New

56 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Code Examples

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

text

pip install git+https://github.com/Disty0/sdnq

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

pythonpytorch

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-Krea-dev-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A frog holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=4.5,
    generator=torch.manual_seed(0),
).images[0]
image.save("flux-krea-dev-sdnq-uint4-svd-r32.png.png")

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.